CN107402931A - Recommend method and apparatus to a kind of trip purpose - Google Patents
Recommend method and apparatus to a kind of trip purpose Download PDFInfo
- Publication number
- CN107402931A CN107402931A CN201610340879.3A CN201610340879A CN107402931A CN 107402931 A CN107402931 A CN 107402931A CN 201610340879 A CN201610340879 A CN 201610340879A CN 107402931 A CN107402931 A CN 107402931A
- Authority
- CN
- China
- Prior art keywords
- information
- mrow
- probability
- destination
- destination information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Abstract
Recommend method and apparatus the invention discloses a kind of trip purpose.This method includes receiving the destination recommendation request information that UE is sent when starting taxi-hailing software, and the destination recommendation request information carries the mark of the UE and starts time point；The History Order information associated in preset time with the mark of the UE is obtained according to the mark of the UE and the startup time point；According to the History Order information and the startup time point, determine that the UE selects the probability of each destination information in the History Order information；The probability of each destination information and the destination information is sent to the UE, so that the UE filters out destination information to be recommended according to the probability from each destination information.History Order information of the invention based on terminal, the destination information for the startup time point terminal opened in taxi-hailing software is predicted, so that the destination to be reached may be selected without carrying out complicated operation in user, Consumer's Experience can be effectively improved.
Description
Technical field
The present invention relates to field of computer technology, and in particular to recommends method and apparatus to a kind of trip purpose.
Background technology
At present, people from being currently located is directed to destination and carries out the guider of road guiding or to peripheral facility
The on-vehicle informations such as the information provider unit retrieved have been popularized.For the service of calling a taxi, user is opening taxi-hailing software
Using call a taxi business when, in order to using the navigation feature of these equipment, it is necessary to which being manually entered needs the destination that reaches.
But the sometimes input of destination information is very cumbersome, it is necessary to spend the time, and sometimes it is also easy to malfunction,
Cause poor user experience.
The content of the invention
For in the prior art the defects of, recommend method and apparatus the invention provides a kind of trip purpose, solve
When business is called a taxi in use, user will be manually entered destination information every time, the problem of causing poor user experience.
In a first aspect, the present invention recommends method with proposing a kind of trip purpose, including：
Receive the destination recommendation request information that UE is sent when starting taxi-hailing software, the destination recommendation request information
Carry the mark of the UE and start time point；
Obtain in preset time and gone through with what the mark of the UE associated according to the mark of the UE and the startup time point
History sequence information；
According to the History Order information and the startup time point, determine that the UE is selected in the History Order information
The probability of each destination information；
The probability of the destination information is selected to send to the UE each destination information and UE selections, with
The UE is set to filter out the destination information recommended to user from each destination information according to the probability.
Preferably, the History Order information includes：At least one destination information and each destination information place an order
Time point；
Correspondingly, it is described according to the History Order information and the startup time point, determine to go through described in the UE selections
The step of probability of destination information in history sequence information, specifically includes：
The distributed data in time-domain of each destination information is obtained according to lower single time point；
The probability of the UE selections each destination information is determined according to the distributed data and the startup time point.
Preferably, it is described according to the distributed data and the startup time point determines UE selection each destination letter
The step of probability of breath, specifically includes：
The probability density function of each destination information is obtained according to the distributed data；
Determine the probability model is established according to the probability density function, and according to the probability determination module and the startup
Time point determines the probability of the UE selections each destination information.
Preferably, the determine the probability model is
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│
T it is) in the probability for starting UE described in time point and selecting i-th of destination information, P (Xi) it is that the UE selects i-th of mesh
Ground information probability,F (t) is the probability density function.
Preferably, determined described according to the History Order information and the startup time point described in the UE selections
Before the step of probability of each destination information in History Order information, this method also includes：
According to the occurrence number of each destination information of History Order acquisition of information；
Occurrence number is filtered out more than or equal to predetermined threshold value from each destination information according to the occurrence number
Destination information.
Second aspect, a kind of the invention also provides trip purpose recommendation apparatus, including：
Receiving module, the destination recommendation request information sent for receiving UE when starting taxi-hailing software, the purpose
Ground recommendation request information carries the mark of the UE and starts time point；
Acquisition module, obtained for the mark according to the UE and the startup time point in preset time with the UE's
Identify the History Order information of association；
Determining module, for according to the History Order information and the startup time point, determining described in the UE selections
The probability of each destination information in History Order information；
Sending module, for selecting the probability of the destination information to send out each destination information and UE selections
The UE is delivered to, so that the UE filters out the destination letter recommended to user according to the probability from each destination information
Breath.
Preferably, the History Order information includes：At least one destination information and each destination information place an order
Time point；
Correspondingly, the determining module, be additionally operable to according to lower single time point obtain each destination information when
Between distributed data on domain；The UE selections each destination information is determined according to the distributed data and the startup time point
Probability.
Preferably, the determining module, the probability for being additionally operable to obtain each destination information according to the distributed data are close
Spend function；Determine the probability model is established according to the probability density function, and according to the probability determination module and the startup
Time point determines the probability of the UE selections each destination information.
Preferably, the determine the probability model is
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│
T it is) in the probability for starting UE described in time point and selecting i-th of destination information, P (Xi) it is that the UE selects i-th of mesh
Ground information probability,F (t) is the probability density function.
Preferably, the device also includes：Screening module；
The screening module, for described according to the History Order information and the startup time point, it is determined that described
Before UE selects the probability of each destination information in the History Order information, according to each purpose of History Order acquisition of information
The occurrence number of ground information；Occurrence number is filtered out according to the occurrence number from each destination information to be more than or equal in advance
If the destination information of threshold value.
As shown from the above technical solution, History Order letter of the method based on terminal is recommended to trip purpose proposed by the present invention
Breath, the destination information for the startup time point terminal opened in taxi-hailing software is predicted, so that user is without carrying out complicated behaviour
Make that the destination to be reached may be selected, Consumer's Experience can be effectively improved.
Brief description of the drawings
The features and advantages of the present invention can be more clearly understood by reference to accompanying drawing, accompanying drawing is schematically without that should manage
Solve to carry out any restrictions to the present invention, in the accompanying drawings：
Fig. 1 be the trip purpose that the embodiment of the disclosure one provides recommend the schematic flow sheet of method；
Fig. 2 be the trip purpose that the embodiment of the disclosure one provides in recommendation method the distributed data of a destination information show
It is intended to；
Fig. 3 be the trip purpose that the embodiment of the disclosure one provides in recommendation method another object information distributed data
Schematic diagram；
Fig. 4 be the trip purpose that the embodiment of the disclosure one provides in recommendation method under the expression of vectorization of single time show
It is intended to；
Fig. 5 be the trip purpose that the embodiment of the disclosure one provides in recommendation method under single time vector conversion expression
Schematic diagram；
Fig. 6 be the embodiment of the disclosure one provide trip purpose recommendation apparatus structural representation.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained on the premise of creative work is not made, belongs to the scope of protection of the invention.
The partial words referred in the embodiment of the present invention are illustrated below.
The user equipment (User Equipment, abbreviation UE) referred in the embodiment of the present invention refers to calling service side, such as
Passenger in vehicles dial-a-cab, used mobile terminal or personal computer (Personal Computer, abbreviation
The equipment such as PC).Such as smart mobile phone, personal digital assistant (PDA), tablet personal computer, notebook computer, vehicle-mounted computer
(carputer), handheld device, intelligent glasses, intelligent watch, wearable device, virtual display device or display enhancing equipment
(such as Google Glass, Oculus Rift, Hololens, Gear VR).
The terminal referred in the embodiment of the present invention, such as the driver in vehicles dial-a-cab, is made to provide service side
It is used for the equipment such as mobile terminal or the PC ends of order.It is all as above-mentioned calling service side uses each equipment.Therefore, this implementation
In example, mobile terminal that first terminal is held by first driver, the terminal ... ... that second terminal is held by second driver,
The terminal that N terminals are held by n-th driver.In the present embodiment, in order to distinguish passenger and driver, user equipment (UE) is respectively adopted
The equipment such as mobile terminal that passenger and driver are held are represented respectively with terminal.
Fig. 1 be the trip purpose that the embodiment of the disclosure one provides recommend the schematic flow sheet of method, reference picture 1, the party
Method includes：
110th, server receives the destination recommendation request information that UE is sent when starting taxi-hailing software, and the destination pushes away
Solicited message is recommended to carry the mark of the UE and start time point；
It will be appreciated that server is after UE destination recommendation request information is received, it will destination is recommended
Solicited message is identified, obtain the UE mark and and start time point, can also obtain the positional information of the UE if necessary
And the corresponding relation between positional information and temporal information.
120th, obtain in preset time and associated with the mark of the UE according to the mark of the UE and the startup time point
History Order information；
It will be appreciated that after the identity of the UE is identified, server will extract the history associated with the UE in database
Sequence information, or the History Order information associated with the UE is obtained by way of loading；
In addition, preset time herein can be 1 week, 10 days etc., it can specifically depend on the circumstances, no longer be limited herein
It is fixed.
130th, according to the History Order information and the startup time point, determine that the UE selects the History Order letter
The probability of each destination information in breath；
It should be noted that because the History Order information before each terminal is not quite similar, therefore, predict that the UE is being opened
The result of the probability of dynamic time each destination information of point selection also differs.
140th, the probability of the destination information is selected to send to described each destination information and UE selections
UE, so that the UE filters out the destination information recommended to user according to the probability from each destination information.
It will be appreciated that server is believed the probability for calculating the UE selection each destination information obtained with corresponding destination
After breath is associated, send to UE.UE will be according to default threshold value to each destination after the information of server transmission is received
Information is filtered out, and the destination information filtered out is illustrated in the recommendation of first screen destination.
For example, the destination information that server is sent includes A, B and C, wherein, the probability that A, B and C are chosen by UE point
Wei a, b and c, it is assumed that the magnitude relationship of predetermined threshold value d and a, b, c in UE are a<b<d<C, then UE will be mesh corresponding with c
Ground information C be illustrated in during first screen destination recommends.
History Order information of the invention based on terminal, predict the mesh for the startup time point terminal opened in taxi-hailing software
Ground information so that the destination to be reached may be selected without carrying out complicated operation in user, user's body can be effectively improved
Test.
Table 1 is the example of History Order information in the present embodiment, and History Order information includes：At least one destination information
With lower single time point of each destination information；
With reference to table 1, History Order information includes：No. 6 doors of Zhongguancun Software Park, the building of Jin Gu gardens the 1st etc.；Lower single time point
Including：2015/1210 10:05 etc.；
| 2015/12/10 10:05 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/10 15:58 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/10 18:52 | The building of Jin Gu gardens the 1st |
| 2015/12/11 18:57 | The building of Jin Gu gardens the 1st |
| 2015/12/11 9:43 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/14 10:05 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/14 20:27 | The building of Jin Gu gardens the 1st |
| 2015/12/14 9:57 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/15 18:02 | The building of Jin Gu gardens the 1st |
| 2015/12/15 19:00 | Zhichun Road |
| 2015/12/15 21:03 | The building of Jin Gu gardens the 1st |
| 2015/12/15 9:54 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/16 19:18 | The building of Jin Gu gardens the 1st |
| 2015/12/16 9:56 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/17 18:38 | Five road junctions shopping center |
| 2015/12/17 9:56 | No. 6 doors of Zhongguancun Software Park |
| 2015/12/18 18:11 | The building of Jin Gu gardens the 1st |
| 2015/12/18 22:30 | The Capital Airport |
| 2015/12/18 8:41 | No. 6 doors of Zhongguancun Software Park |
Table 1
Fig. 2 and Fig. 3 is respectively the trip purpose that the embodiment of the disclosure one provides ground destination information in recommendation method
Distributed data schematic diagram, referring to Fig. 2 and Fig. 3, step 130 is described in detail：
The distributed data in time-domain of each destination information is obtained according to lower single time point；
It will be appreciated that the abscissa in Fig. 2 and Fig. 3 is the time, ordinate is frequency；As shown in Figure 2, it is soft with Zhong Guan-cun
When the door of part garden 6 is destination information, lower single time point of terminal concentrates at 9 points, 10 points；
From the figure 3, it may be seen that during using the building of Jin Gu gardens the 1st as destination information, lower single time point of terminal concentrates on 18-21 points.
The probability of the UE selections each destination information is determined according to the distributed data and the startup time point.
In the present embodiment, step 130 specifically includes：
The probability density function of each destination information is obtained according to the distributed data；
Determine the probability model is established according to the probability density function, and according to the probability determination module and the startup
Time point determines the probability of the UE selections each destination information.
Step 130 is described in detail below：
The present invention estimates the probability that each destination is believed by the distributed data in time-domain of each destination information
Density function f (t).
Above-mentioned determine the probability model is
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│
T it is) in the probability for starting UE described in time point and selecting i-th of destination information, P (Xi) it is that the UE selects i-th of mesh
Ground information probability,F (t) is the probability density function.
Further, the determination in this step on f (t), there is several alternative, said by taking Gaussian Profile as an example
It is bright, it is as follows：
It is assumed here that terminal is in history, bill goes the Annual distribution of same destination to obey N (μ, σ2), wherein μ and σ difference
It is the average and standard deviation of the destination historical time.
Density function：
Distribution function：
According to N (μ, σ above2) distribution function calculated, obtain below equation：
P(T|Xi)=F (T+ Δ t)-F (T- Δs t)
Next it is converted into standard and is just distributed very much, according to theorem,
Then：
So
In order to improve the support of prediction and confidence level, before step 130, this method also includes：
According to the occurrence number of each destination information of History Order acquisition of information；
It should be noted that the same destination information in believing History Order adds up, you can obtains each purpose
The occurrence number of ground information.
Occurrence number is filtered out more than or equal to predetermined threshold value from each destination information according to the occurrence number
Destination information.
Predetermined threshold value herein can depend on the circumstances, and it is relevant with above-mentioned preset time, for example, above-mentioned
Preset time it is larger when, predetermined threshold value is then relatively also larger herein；When above-mentioned preset time is smaller, predetermined threshold value is relative
Also to diminish；Both corresponding relations are no longer defined herein.
In order to improve optimization this recommendation method, detect that server sends the selected probability of each destination information in UE
Be below terminal setting threshold value when, and can not generate need recommend destination information when, then to server feedback without recommendation
Information；
Server is then adjusted when receiving no recommendation information to the predetermined threshold value on occurrence number, so as to
Satisfactory probability be present in the probability for each destination information that UE is sent, prevent the situation for not recommending destination.
It will be appreciated that because the trip data of each user in itself is than sparse, along with not enough uniformly, just as above-mentioned
Example, in addition to the destination that two comparisons are concentrated, other several destinations only occur 1~2 time, one so brought
Problem is exactly that the standard deviation sigma of normal distyribution function that fits can be made minimum.
One penalty coefficient is increased to standard deviation sigma for this present invention：
Wherein c is the number that a destination information occurs.
Further, although in theory, the codomain of normal distribution is (- ∞ ,+∞), in fact, being in (- 3 σ ,+3 σ)
The probability in section has reached 0.999.
Therefore, the present invention sets a minimum 0.0001 to the probability more than (- 3 σ ,+3 σ) section.
The principle of the present invention is described in detail below：
Above-mentioned table 1 is handled, processing step includes：
1st, date, a retention time are removed；
2nd, will be digitized the time, such as：9:30->9.5,22:20->22.3, obtain table 2.
Table 2
| Destination | Annual distribution |
| No. 6 doors of Zhongguancun Software Park | 8.7,9.7,9.9,9.9,9.9,10,10.1,10.1,16 |
| The building of Jin Gu gardens the 1st | 18,18.2,18.9,19,19.3,20.5,21.1 |
| Zhichun Road | 19 |
| Five road junctions shopping center | 18.6 |
| The Capital Airport | 22.5 |
As can be seen that in addition to individual noise point, rule is clearly：Morning 9~10 point hair bill goes to company (Zhong Guan-cun
Software centre), go home (Jin Guyuan) for 18~21 points at night.
In order to quantify compact/sparse degree of the Annual distribution of each destination and the frequent degree of the destination, this hair
It is bright to use 3 statistical indicators：Average e, standard deviation d, frequency f.
Above in three variables, average e calculating is relatively difficult, it is clear that can not simply add all moment and ask flat
, such as：8 points, 9 points, 10 points of the moment, then the average moment should be 9 points；23 points of moment, 0 point, 4 points, then averagely the moment is 1
Point.
Fig. 4 and Fig. 5 be respectively the trip purpose that the embodiment of the disclosure one provides in recommendation method under single time vector
Change the expression schematic diagram with vector conversion, the representation for being converted into vector to lower single time referring to Fig. 4 and Fig. 5 is carried out in detail
Explanation：
Disk represents clock face, and two reference axis are respectively x, y-axis, and three vectors on Fig. 4 from top to bottom distinguish table
It is at the time of showing：3 points, 22 points, 23 points, circular arc arrow represents the direction of clock.
So, at the average moment at three moment above, these three vectors can be summed up, and vector fall dial plate
On position be average moment, such as Fig. 5：
The average moment at 3 points, 22 points, 23 points 3 moment is 0 point, and vector fall dial plate on position be also precisely
0 point.
Specific calculation procedure is as follows：
Step1：I-th of moment xiVector representation
(cosθi,sinθi)
Step2：Calculate vectorial and vectorial corresponding to n moment
Step3：Calculating and vector and the angle of x-axis：
Step4：By θtAt the time of being converted to corresponding：
Tri- places of A, B, C, current time T assuming that user's history got on, then need to calculate three conditional probabilities：
P (A | T), P (B | T), P (C | T) if some probability is won with absolute predominance, and have enough supports, then
First screen recommendation ought to be used as to be shown.
Directly calculating P (A | T) it is relatively difficult, we enter line translation using Bayesian formula
We use XiRepresent i-th of address, then according to total probability formula,
Finally,
With the data instance in table 1：
Data first in table 1, which calculate, obtains following table 3；
| Destination | Annual distribution | Distribution index |
| No. 6 doors of Zhongguancun Software Park | 8.7,9.7,9.9,9.9,9.9,10,10.1,10.1,16 | E=10.5, d=2, f=0.47 |
| The building of Jin Gu gardens the 1st | 18,18.2,18.9,19,19.3,20.5,21.1 | E=19.3, d=0.96, f=0.37 |
| Zhichun Road | 19 | E=19, d=0, f=0.05 |
| Five road junctions shopping center | 18.6 | E=18.6, d=0, f=0.05 |
| The Capital Airport | 22.5 | E=22.5, d=0, f=0.05 |
Table 3
Assuming that current time T=9 points
P (T=9 | No. 6 doors of X=Zhongguancun Software Parks)=0.3, P (No. 6 doors of X=Zhongguancun Software Parks)=0.47
P (T=9 | the building of X=Jin Gu gardens the 1st)=0.05, P (building of X=Jin Gu gardens the 1st)=0.37
P (T=9 | X=Zhichun Roads)=0.02, P (X=Zhichun Roads)=0.05
P (T=9 | the road junction shopping centers of X=five)=0.02, P (the road junction shopping centers of X=five)=0.05
P (T=9 | the X=Capital Airports)=0.01, P (the X=Capital Airports)=0.05
Finally, the probability of each destination is as follows：
P (No. 6 doors of X=Zhongguancun Software Parks | T=9 points)=0.88125
P (building of X=Jin Gu gardens the 1st | T=9 points)=0.115625
P (X=Zhichun Roads | T=9 points)=0.00625
P (the road junction shopping centers of X=five | T=9 points)=0.00625
P (the X=Capital Airports | T=9 points)=0.003125
The data of above-mentioned acquisition are sent to UE by server, it is assumed that the probability threshold value in UE is 0.88, then " Zhong Guan-cun is soft
The door of part garden 6 " will appear in the recommendation of first screen destination.
For method embodiment, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but ability
Field technique personnel should know that embodiment of the present invention is not limited by described sequence of movement, because according to the present invention
Embodiment, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art should also know,
Embodiment described in this description belongs to preferred embodiment, involved action embodiment party not necessarily of the present invention
Necessary to formula.
The trip purpose that Fig. 6 provides for the embodiment of the disclosure one recommendation apparatus structural representation, reference picture 6, should
Device includes：
Receiving module 610, the destination recommendation request information sent for receiving UE when starting taxi-hailing software, the mesh
Ground recommendation request information carry the mark of the UE and start time point；
Acquisition module 620, for the mark according to the UE and it is described startup time point obtain preset time in it is described
The History Order information of UE mark association；
Determining module 630, for according to the History Order information and the startup time point, determining the UE selections institute
State the probability of each destination information in History Order information；
Sending module 640, for each destination information and UE selections to be selected into the general of the destination information
Rate is sent to the UE, so that the UE filters out the destination recommended to user according to the probability from each destination information
Information.
History Order information of the invention based on terminal, predict the mesh for the startup time point terminal opened in taxi-hailing software
Ground information so that the destination to be reached may be selected without carrying out complicated operation in user, user's body can be effectively improved
Test.
In the present embodiment, History Order information includes：At least one destination information and each destination information place an order
Time point；
Correspondingly, the determining module 630, it is additionally operable to be existed according to lower single time point acquisition each destination information
Distributed data in time-domain；The UE selections each destination letter is determined according to the distributed data and the startup time point
The probability of breath.
In a possible embodiments, determining module 630, it is additionally operable to obtain each destination information according to the distributed data
Probability density function；Determine the probability model is established according to the probability density function, and according to the probability determination module and
The startup time point determines the probability of the UE selections each destination information.
In a possible embodiments, determine the probability model is
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│
T it is) in the probability for starting UE described in time point and selecting i-th of destination information, P (Xi) it is that the UE selects i-th of mesh
Ground information probability,F (t) is the probability density function.
In a possible embodiments, the device also includes：Screening module；
The screening module, for described according to the History Order information and the startup time point, it is determined that described
Before UE selects the probability of each destination information in the History Order information, according to each purpose of History Order acquisition of information
The occurrence number of ground information；Occurrence number is filtered out according to the occurrence number from each destination information to be more than or equal in advance
If the destination information of threshold value.
For device embodiments, because it is substantially similar to method embodiment, so description is fairly simple,
Related part illustrates referring to the part of method embodiment.
It should be noted that in all parts of the device of the present invention, according to the function that it to be realized to therein
Part has carried out logical partitioning, and still, the present invention is not only restricted to this, all parts can be repartitioned as needed or
Person combines.
The all parts embodiment of the present invention can be realized with hardware, or to be transported on one or more processor
Capable software module is realized, or is realized with combinations thereof.In the present apparatus, PC is by realizing internet to equipment or device
Remote control, the step of accurately control device or device each operate.The present invention is also implemented as being used to perform here
The some or all equipment or program of device of described method are (for example, computer program and computer program production
Product).Being achieved in that the program of the present invention can store on a computer-readable medium, and file or document caused by program has
Having can be statistical, produces data report and cpk reports etc., and batch testing can be carried out to power amplifier and is counted.On it should be noted that
Stating embodiment, the present invention will be described rather than limits the invention, and those skilled in the art are not departing from
Replacement embodiment can be designed in the case of the scope of attached claim.In the claims, should not will be between bracket
Any reference symbol be configured to limitations on claims.Word "comprising" does not exclude the presence of member not listed in the claims
Part or step.Word "a" or "an" before element does not exclude the presence of multiple such elements.The present invention can borrow
The hardware that helps to include some different elements and realized by means of properly programmed computer.If listing equipment for drying
Unit claim in, several in these devices can be embodied by same hardware branch.Word first,
Second and third use do not indicate that any order.These words can be construed to title.Although it is described in conjunction with the accompanying
Embodiments of the present invention, but those skilled in the art can make without departing from the spirit and scope of the present invention
Various modifications and variations, such modifications and variations are each fallen within be defined by the appended claims within the scope of.
Claims (10)
1. recommend method to a kind of trip purpose, it is characterised in that including：
The destination recommendation request information that UE is sent when starting taxi-hailing software is received, the destination recommendation request information carries
The mark of the UE and startup time point；
The history associated with the mark of the UE in preset time is obtained according to the mark of the UE and the startup time point to order
Single information；
According to the History Order information and the startup time point, determine that the UE selects each mesh in the History Order information
Ground information probability；
The probability of the destination information is selected to send to the UE each destination information and UE selections, so that institute
State UE and filter out the destination information recommended to user from each destination information according to the probability.
2. according to the method for claim 1, it is characterised in that the History Order information includes：At least one destination
Lower single time point of information and each destination information；
Correspondingly, it is described according to the History Order information and the startup time point, determine that the UE selects the history to order
The step of probability of destination information in single information, specifically includes：
The distributed data in time-domain of each destination information is obtained according to lower single time point；
The probability of the UE selections each destination information is determined according to the distributed data and the startup time point.
3. according to the method for claim 2, it is characterised in that described according to the distributed data and the startup time point
The step of probability for determining the UE selections each destination information, specifically includes：
The probability density function of each destination information is obtained according to the distributed data；
Determine the probability model is established according to the probability density function, and according to the probability determination module and the startup time
Point determines the probability of the UE selections each destination information.
4. according to the method for claim 3, it is characterised in that the determine the probability model is
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>T</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>T</mi>
<mo>|</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>*</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
<mo>&lsqb;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>T</mi>
<mo>|</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>*</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
</mfrac>
</mrow>
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│ T) be
The probability of i-th of destination information, P (X are selected in UE described in the startup time pointi) it is that the UE selects i-th of destination
The probability of information,F (t) is the probability density function.
5. according to the method described in claim any one of 1-4, it is characterised in that it is described according to the History Order information and
The startup time point, determine the step of UE selects the probability of each destination information in the History Order information it
Before, this method also includes：
According to the occurrence number of each destination information of History Order acquisition of information；
The purpose that occurrence number is more than or equal to predetermined threshold value is filtered out from each destination information according to the occurrence number
Ground information.
A kind of 6. trip purpose ground recommendation apparatus, it is characterised in that including：
Receiving module, the destination recommendation request information sent for receiving UE when starting taxi-hailing software, the destination pushes away
Solicited message is recommended to carry the mark of the UE and start time point；
Acquisition module, for the mark according to the UE and the mark started in time point acquisition preset time with the UE
The History Order information of association；
Determining module, for according to the History Order information and the startup time point, determining that the UE selects the history
The probability of each destination information in sequence information；
Sending module, for by each destination information and UE selections select the probability of the destination information send to
The UE, so that the UE filters out the destination information recommended to user according to the probability from each destination information.
7. device according to claim 6, it is characterised in that the History Order information includes：At least one destination
Lower single time point of information and each destination information；
Correspondingly, the determining module, it is additionally operable to according to lower single time point acquisition each destination information in time-domain
On distributed data；The general of the UE selections each destination information is determined according to the distributed data and the startup time point
Rate.
8. device according to claim 7, it is characterised in that the determining module, be additionally operable to according to the distributed data
Obtain the probability density function of each destination information；Determine the probability model is established according to the probability density function, and according to
The probability determination module and the startup time point determine the probability of the UE selections each destination information.
9. device according to claim 8, it is characterised in that the determine the probability model is
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>T</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>T</mi>
<mo>|</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>*</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
<mo>&lsqb;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>T</mi>
<mo>|</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>*</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
</mfrac>
</mrow>
Wherein, n >=1, T are the startup time point, XiFor i-th of destination information in History Order information, P (Xi│ T) be
The probability of i-th of destination information, P (X are selected in UE described in the startup time pointi) it is that the UE selects i-th of destination
The probability of information,F (t) is the probability density function.
10. according to the device described in claim any one of 6-9, it is characterised in that the device also includes：Screening module；
The screening module, for, according to the History Order information and the startup time point, determining the UE choosings described
Before the probability for selecting each destination information in the History Order information, believed according to each destination of the History Order acquisition of information
The occurrence number of breath；Occurrence number is filtered out from each destination information according to the occurrence number and is more than or equal to default threshold
The destination information of value.
Priority Applications (14)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610340879.3A CN107402931A (en) | 2016-05-19 | 2016-05-19 | Recommend method and apparatus to a kind of trip purpose |
| SG11201801375UA SG11201801375UA (en) | 2015-08-20 | 2016-08-22 | Systems and methods for determining information related to a current order based on historical orders |
| EP16836685.4A EP3340092A4 (en) | 2015-08-20 | 2016-08-22 | Method and system for predicting current order information on the basis of historical order |
| PCT/CN2016/096222 WO2017028821A1 (en) | 2015-08-20 | 2016-08-22 | Method and system for predicting current order information on the basis of historical order |
| GB1802571.8A GB2556780A (en) | 2015-08-20 | 2016-08-22 | Method and system for predicting current order information on the basis of historical order |
| KR1020187006029A KR20180037015A (en) | 2015-08-20 | 2016-08-22 | System and method for determining information related to a current order based on past orders |
| AU2016309857A AU2016309857A1 (en) | 2015-08-20 | 2016-08-22 | Systems and methods for determining information related to a current order based on historical orders |
| JP2018508657A JP2018528535A (en) | 2015-08-20 | 2016-08-22 | System and method for determining information related to a current order based on past orders |
| US15/896,035 US20180181910A1 (en) | 2015-08-20 | 2018-02-13 | Systems and methods for determining information related to a current order based on historical orders |
| PH12018550018A PH12018550018A1 (en) | 2015-08-20 | 2018-02-20 | Systems and methods for determining information related to a current order based on historical orders |
| HK18113333.9A HK1254330A1 (en) | 2015-08-20 | 2018-10-18 | Method and system for predicting current order information on the basis of historical order |
| AU2019101777A AU2019101777A4 (en) | 2015-08-20 | 2019-11-20 | Systems and methods for determining information related to a current order based on historical orders |
| AU2019268117A AU2019268117A1 (en) | 2015-08-20 | 2019-11-20 | Systems and methods for determining information related to a current order based on historical orders |
| JP2020009028A JP6878629B2 (en) | 2015-08-20 | 2020-01-23 | Systems and methods for determining information related to the current order based on past orders |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610340879.3A CN107402931A (en) | 2016-05-19 | 2016-05-19 | Recommend method and apparatus to a kind of trip purpose |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107402931A true CN107402931A (en) | 2017-11-28 |
Family
ID=60389249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610340879.3A Pending CN107402931A (en) | 2015-08-20 | 2016-05-19 | Recommend method and apparatus to a kind of trip purpose |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107402931A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949068A (en) * | 2019-01-09 | 2019-06-28 | 深圳北斗应用技术研究院有限公司 | A kind of real time pooling vehicle method and apparatus based on prediction result |
| CN109992726A (en) * | 2018-10-17 | 2019-07-09 | 招商银行股份有限公司 | Position predicting method, device and readable storage medium storing program for executing |
| WO2019183844A1 (en) * | 2018-03-28 | 2019-10-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining passenger-seeking ride-sourcing vehicle navigation |
| WO2020000277A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for predicting destination in online to offline service |
| CN110689158A (en) * | 2018-07-05 | 2020-01-14 | 北京嘀嘀无限科技发展有限公司 | Method, device and storage medium for predicting destination |
| CN110796278A (en) * | 2019-10-22 | 2020-02-14 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN110889732A (en) * | 2018-09-07 | 2020-03-17 | 北京嘀嘀无限科技发展有限公司 | Takeout order generation method, device and equipment |
| CN111142719A (en) * | 2018-11-02 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Service pushing method and device |
| CN111310961A (en) * | 2018-12-12 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Data prediction method, data prediction device, electronic equipment and computer readable storage medium |
| CN111835810A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Destination pushing method and device, electronic equipment and storage medium |
| CN111859169A (en) * | 2019-06-05 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Destination recommendation method and system |
| CN112055867A (en) * | 2018-05-18 | 2020-12-08 | 北京嘀嘀无限科技发展有限公司 | System and method for recommending personalized boarding location |
| CN112883291A (en) * | 2021-02-05 | 2021-06-01 | 上海钧正网络科技有限公司 | Destination position recommendation method and device and server |
| CN113050856A (en) * | 2021-03-23 | 2021-06-29 | 北京嘀嘀无限科技发展有限公司 | Interaction method, interaction device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082227A1 (en) * | 2008-09-17 | 2010-04-01 | Harman Becker Automotive Systems Gmbh | Method for displaying traffic density information |
| CN103674042A (en) * | 2012-09-18 | 2014-03-26 | 三星电子（中国）研发中心 | Route guide system and method based on user modeling |
| CN104520881A (en) * | 2012-06-22 | 2015-04-15 | 谷歌公司 | Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location history |
| CN104599217A (en) * | 2015-01-27 | 2015-05-06 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining current destination of passenger |
| CN104899252A (en) * | 2015-05-12 | 2015-09-09 | 北京嘀嘀无限科技发展有限公司 | Information push method and apparatus |
-
2016
- 2016-05-19 CN CN201610340879.3A patent/CN107402931A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082227A1 (en) * | 2008-09-17 | 2010-04-01 | Harman Becker Automotive Systems Gmbh | Method for displaying traffic density information |
| CN104520881A (en) * | 2012-06-22 | 2015-04-15 | 谷歌公司 | Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location history |
| CN103674042A (en) * | 2012-09-18 | 2014-03-26 | 三星电子（中国）研发中心 | Route guide system and method based on user modeling |
| CN104599217A (en) * | 2015-01-27 | 2015-05-06 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining current destination of passenger |
| CN104899252A (en) * | 2015-05-12 | 2015-09-09 | 北京嘀嘀无限科技发展有限公司 | Information push method and apparatus |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019183844A1 (en) * | 2018-03-28 | 2019-10-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining passenger-seeking ride-sourcing vehicle navigation |
| US11094028B2 (en) | 2018-03-28 | 2021-08-17 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining passenger-seeking ride-sourcing vehicle navigation |
| CN112055867A (en) * | 2018-05-18 | 2020-12-08 | 北京嘀嘀无限科技发展有限公司 | System and method for recommending personalized boarding location |
| CN110869951A (en) * | 2018-06-28 | 2020-03-06 | 北京嘀嘀无限科技发展有限公司 | System and method for predicting destinations in online-to-offline service |
| CN110869951B (en) * | 2018-06-28 | 2023-11-14 | 北京嘀嘀无限科技发展有限公司 | System and method for predicting destination in online-to-offline service |
| WO2020000277A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for predicting destination in online to offline service |
| CN110689158A (en) * | 2018-07-05 | 2020-01-14 | 北京嘀嘀无限科技发展有限公司 | Method, device and storage medium for predicting destination |
| CN110689158B (en) * | 2018-07-05 | 2022-05-31 | 北京嘀嘀无限科技发展有限公司 | Method, device and storage medium for predicting destination |
| CN110889732A (en) * | 2018-09-07 | 2020-03-17 | 北京嘀嘀无限科技发展有限公司 | Takeout order generation method, device and equipment |
| CN109992726A (en) * | 2018-10-17 | 2019-07-09 | 招商银行股份有限公司 | Position predicting method, device and readable storage medium storing program for executing |
| CN111142719A (en) * | 2018-11-02 | 2020-05-12 | 北京嘀嘀无限科技发展有限公司 | Service pushing method and device |
| CN111310961A (en) * | 2018-12-12 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Data prediction method, data prediction device, electronic equipment and computer readable storage medium |
| CN109949068A (en) * | 2019-01-09 | 2019-06-28 | 深圳北斗应用技术研究院有限公司 | A kind of real time pooling vehicle method and apparatus based on prediction result |
| CN111859169A (en) * | 2019-06-05 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Destination recommendation method and system |
| CN111835810A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Destination pushing method and device, electronic equipment and storage medium |
| CN110796278A (en) * | 2019-10-22 | 2020-02-14 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN110796278B (en) * | 2019-10-22 | 2021-09-07 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN112883291A (en) * | 2021-02-05 | 2021-06-01 | 上海钧正网络科技有限公司 | Destination position recommendation method and device and server |
| CN113050856A (en) * | 2021-03-23 | 2021-06-29 | 北京嘀嘀无限科技发展有限公司 | Interaction method, interaction device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107402931A (en) | Recommend method and apparatus to a kind of trip purpose | |
| CN107798412B (en) | Route recommendation method and device | |
| US20170293847A1 (en) | Crime risk forecasting | |
| CN109151168B (en) | Switching method and device of riding codes, mobile terminal and readable storage medium | |
| CN110147967B (en) | Risk prevention and control method and device | |
| KR20180013843A (en) | Order allocation system and method | |
| CN106919993A (en) | A kind of high accuracy acquiescence destination Forecasting Methodology and device based on historical data | |
| CN107230046A (en) | The reminding method and mobile terminal of a kind of trip information | |
| CN110929799B (en) | Method, electronic device, and computer-readable medium for detecting abnormal user | |
| CN104867065A (en) | Method and equipment for processing orders | |
| CN106919996A (en) | A kind of destination Forecasting Methodology and device | |
| US20160055431A1 (en) | System and method for generating itineraries and weather forecast displays | |
| CN109785000A (en) | Customer resources distribution method, device, storage medium and terminal | |
| CN108549990A (en) | Declaration form distribution method, device, computer equipment and storage medium | |
| US11651320B2 (en) | Presentation device and presentation method | |
| CN109685234A (en) | The processing method and system subscribed for hotel's house type | |
| CN111859172B (en) | Information pushing method, device, electronic equipment and computer readable storage medium | |
| CN107895537A (en) | A kind of display methods of electronic map, relevant apparatus and storage medium | |
| US11403572B2 (en) | Method and system for requesting service providers in real time | |
| Wang et al. | Province-level estimation of waste mobile phones in China and location planning of recycling centers | |
| CN109658187A (en) | Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider | |
| CN105787789A (en) | Method and apparatus for displaying currency exchange rate | |
| CN105608921A (en) | Method and equipment for prompting public transport line in electronic device | |
| CN109344247A (en) | Method and apparatus for output information | |
| CN114970495A (en) | Name disambiguation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201215 Address after: No.8, Dongbei Wangxi Road, Haidian District, Beijing 100193 Applicant after: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT Co.,Ltd. Address before: Room 219-23, 2 / F, block D, comprehensive service area, Nangang Industrial Zone, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin 300480 Applicant before: Didi (China) Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20220118 |
|
| AD01 | Patent right deemed abandoned |